Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference

• URL: http://arxiv.org/abs/2609.09628v1
• Date: Wed, 09 Sep 2026 02:40:02 GMT
• Title: Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference
• Abstract summary: Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding.<n>Existing inference-time LLM approaches provide limited structure for handling subtle, distributed, and multimodal relational cues.<n>We introduce a training-free multi-agent reasoning framework that organizes inference through structured interaction among LLM agents.
• Score: 18.334093251358833
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding. However, this task remains underexplored, and supervised modeling is costly to train and scale. At the same time, existing inference-time LLM approaches provide limited structure for handling subtle, distributed, and multimodal relational cues that may support multiple plausible interpretations. To address these limitations, we introduce a training-free multi-agent reasoning framework that organizes inference through structured interaction among LLM agents, allowing relationship judgments to be proposed, challenged, and adjudicated without task-specific training. We instantiate this framework with two complementary designs. We propose Multi-Role Multi-Agent Debate as a task-specific adaptation of standard multi-agent debate for speaker relationship inference, assigning agents complementary roles or social-theory-grounded perspectives rather than a single undifferentiated viewpoint. In contrast, we introduce Multi-Agent Compete, a competition-based protocol that compares agent judgments through pairwise adjudication, eliminates weaker candidates, and retains the most defensible one. We evaluate these methods on the Seamless Interaction dataset across different modality settings, covering both binary classification and fine-grained relationship-detail prediction. Results suggest that they improve over zero-shot and existing multi-agent baselines in most cases. Human evaluation further suggests that this task is challenging even for people. LLM methods can sometimes outperform human annotators in text-included settings but are less competitive in the audio setting. Together, these findings suggest that relationship inference benefits from structured inference-time interaction among agents, while acoustic cues are not yet fully captured by current models.

Related papers

• MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant [138.90198190949545]
  We introduce MP-Bench, the first benchmark specifically designed to evaluate conversational speech systems as active participants within multi-party contexts.<n>MP-Bench assesses agent behavior along two primary dimensions: turn-taking awareness and response appropriateness.<n>We find that real-time voice agents stay at or below 22% on multiparty comprehension and remain near chance on multiparty turn-taking.
  arXiv  Detail & Related papers  (2026-09-11T17:11:55Z)
• When Contextual Inference Fails: Cancelability in Interactive Instruction Following [51.2195840589474]
  We introduce Build What I Mean, an interactive benchmark for contextual meaning construction.<n>In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost.<n>We observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
  arXiv  Detail & Related papers  (2026-03-20T14:46:59Z)
• AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding [73.05946667683259]
  Recent large language models (MLLMs) show strong perception but struggle in multi-speaker, dialogue-centric settings.<n>We introduce AMUSE, a benchmark designed around tasks that are inherently agentic.<n>We propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation.
  arXiv  Detail & Related papers  (2025-12-18T07:01:47Z)
• DEBATE: A Large-Scale Benchmark for Role-Playing LLM Agents in Multi-Agent, Long-Form Debates [10.609797175227644]
  We introduce DEBATE, the first large-scale empirical benchmark to evaluate the authenticity of the interaction between multi-agent role-playing LLMs.<n>We systematically evaluate and identify critical discrepancies between simulated and authentic group dynamics.
  arXiv  Detail & Related papers  (2025-10-29T02:21:10Z)
• OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning [14.105640933123325]
  Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks.<n>To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.<n>We propose $ours$, a multi-agent verbal reinforcement learning algorithm that dynamically constructs and refines multi-agent collaboration structures.
  arXiv  Detail & Related papers  (2025-10-20T19:07:51Z)
• Benefits and Limitations of Communication in Multi-Agent Reasoning [11.788489289062312]
  We propose a theoretical framework to analyze the expressivity of multi-agent systems.<n>We derive bounds on (i) the number of agents required to solve the task exactly, (ii) the quantity and structure of inter-agent communication, and (iii) the achievable speedups as problem size and context scale.<n>Our results identify regimes where communication is provably beneficial, delineate tradeoffs between agent count and bandwidth, and expose intrinsic limitations when either resource is constrained.
  arXiv  Detail & Related papers  (2025-10-14T20:04:27Z)
• Let's Roleplay: Examining LLM Alignment in Collaborative Dialogues [11.888786446094057]
  This paper examines how different alignment methods affect Large Language Models' effectiveness as partners in multiturn, multiparty collaborations.<n>Using a roleplay methodology, we evaluate interventions from differently-trained friction agents in collaborative task conversations.<n>Our results show that a friction-aware approach significantly outperforms common alignment baselines in helping both convergence to a common ground, or agreed-upon task-relevant propositions, and correctness of task outcomes.
  arXiv  Detail & Related papers  (2025-09-07T00:58:10Z)
• Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks [81.44256822500257]
  RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences.<n> RLHF exhibits insufficient compliance capabilities when confronted with complex multi-instruction tasks.<n>We propose a novel Multi-level Aware Preference Learning (MAPL) framework, capable of enhancing multi-instruction capabilities.
  arXiv  Detail & Related papers  (2025-05-19T08:33:11Z)
• Low-rank Prompt Interaction for Continual Vision-Language Retrieval [47.323830129786145]
  We propose the Low-rank Prompt Interaction to address the problem of multi-modal understanding.<n>Considering that the training parameters scale to the number of layers and tasks, we propose low-rank interaction-augmented decomposition.<n>We also adopt hierarchical low-rank contrastive learning to ensure robustness training.
  arXiv  Detail & Related papers  (2025-01-24T10:00:47Z)
• Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications [90.6849884683226]
  We study the challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data. Using a precise information-theoretic definition of interactions, our key contribution is the derivation of lower and upper bounds. We show how these theoretical results can be used to estimate multimodal model performance, guide data collection, and select appropriate multimodal models for various tasks.
  arXiv  Detail & Related papers  (2023-06-07T15:44:53Z)
• Pre-training Multi-party Dialogue Models with Latent Discourse Inference [85.9683181507206]
  We pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model.
  arXiv  Detail & Related papers  (2023-05-24T14:06:27Z)
• Rethinking Trajectory Prediction via "Team Game" [118.59480535826094]
  We present a novel formulation for multi-agent trajectory prediction, which explicitly introduces the concept of interactive group consensus. On two multi-agent settings, i.e. team sports and pedestrians, the proposed framework consistently achieves superior performance compared to existing methods.
  arXiv  Detail & Related papers  (2022-10-17T07:16:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.